• Home
  • Search
  • BSDSNet: Dual-Stream Feature Extraction Network Based on Segment Anything Model for Synthetic Aperture Radar Land Cover Classification
  • Cite Icon7
  • https://doi.org/10.3390/rs16071150Copy DOI Icon

BSDSNet: Dual-Stream Feature Extraction Network Based on Segment Anything Model for Synthetic Aperture Radar Land Cover Classification

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Land cover classification using high-resolution Polarimetric Synthetic Aperture Radar (PolSAR) images obtained from satellites is a challenging task. While deep learning algorithms have been extensively studied for PolSAR image land cover classification, the performance is severely constrained due to the scarcity of labeled PolSAR samples and the limited domain acceptance of models. Recently, the emergence of the Segment Anything Model (SAM) based on the vision transformer (VIT) model has brought about a revolution in the study of specific downstream tasks in computer vision. Benefiting from its millions of parameters and extensive training datasets, SAM demonstrates powerful capabilities in extracting semantic information and generalization. To this end, we propose a dual-stream feature extraction network based on SAM, i.e., BSDSNet. We change the image encoder part of SAM to a dual stream, where the ConvNext image encoder is utilized to extract local information and the VIT image encoder is used to extract global information. BSDSNet achieves an in-depth exploration of semantic and spatial information in PolSAR images. Additionally, to facilitate a fine-grained amalgamation of information, the SA-Gate module is employed to integrate local–global information. Compared to previous deep learning models, BSDSNet’s impressive ability to represent features is akin to a versatile receptive field, making it well suited for classifying PolSAR images across various resolutions. Comprehensive evaluations indicate that BSDSNet achieves excellent results in qualitative and quantitative evaluation when performing classification tasks on the AIR-PolSAR-Seg dataset and the WHU-OPT-SAR dataset. Compared to the suboptimal results, our method improves the Kappa metric by 3.68% and 0.44% on the AIR-PolSAR-Seg dataset and the WHU-OPT-SAR dataset, respectively.

Loading PDF

Similar Papers
  • Research Article
  • Citations2

Exploring the Performance of Different Texture Information and Polarization Features from PolSAR Images in Urban Land Cover Classification

  • Feb 01, 2021
  • Photogrammetric Engineering & Remote Sensing
  • Songjing Guo +2
  • PDF
  • Research Article
  • Citations21

Multi-Feature Segmentation for High-Resolution Polarimetric SAR Data Based on Fractal Net Evolution Approach

  • Jun 06, 2017
  • Remote Sensing
  • Qihao Chen +5
  • Research Article
  • Citations4

A level set method for segmentation of high-resolution polarimetric SAR images using a heterogeneous clutter model

  • Jun 25, 2015
  • Remote Sensing Letters
  • Pengfei Zou +3
  • Research Article
  • Citations3

PolSAR Image Super-Resolution With Polarimetric Degradation Modulation Network

  • Dec 01, 2025
  • IEEE Transactions on Aerospace and Electronic Systems
  • Lin-Yu Dai +2
  • Research Article
  • Citations1

Superpixel Segmentation for PolSAR Images Based on Geodesic Distance

  • Feb 25, 2021
  • SHILAP Revista de lepidopterología
  • Zou Huanxin +4
  • Conference Article

Unsupervised Cross-Domain Network Based on Bi-classifier for PolSAR Image Classification

  • Sep 22, 2023
  • Wenqiang Hua +3
  • Research Article
  • Citations20

Cost-Sensitive Latent Space Learning for Imbalanced PolSAR Image Classification

  • Aug 13, 2020
  • IEEE Transactions on Geoscience and Remote Sensing
  • Qian Wu +4
  • Research Article
  • Citations51

MP-ResNet: Multipath Residual Network for the Semantic Segmentation of High-Resolution PolSAR Images

  • Jan 01, 2022
  • IEEE Geoscience and Remote Sensing Letters
  • Lei Ding +6
  • Research Article
  • Citations10

Composite Kernel Method for PolSAR Image Classification Based on Polarimetric-Spatial Information

  • Jun 13, 2017
  • Applied Sciences
  • Xianyuan Wang +3
  • Research Article
  • Citations10

Polarimetric SAR Image Terrain Classification

  • Nov 01, 2019
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • R Derek West +5
  • Research Article
  • Citations6

Superpixel-Oriented Unsupervised Classification for Polarimetric SAR Images Based on Consensus Similarity Network Fusion

  • Jan 01, 2019
  • IEEE Access
  • Huanxin Zou +3
  • Research Article
  • Citations26

Low-Resolution Fully Polarimetric SAR and High-Resolution Single-Polarization SAR Image Fusion Network

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Liupeng Lin +5
  • Research Article
  • Citations9

Independent Target Detection of PolSAR Image Joint Polarimetric and Spatial Features Based on Adaptive Convolution Sparse Representation

  • Dec 05, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Lamei Zhang +3
  • Research Article
  • Citations1

Segmentation of multi-temporal polarimetric SAR data based on mean-shift and spectral graph partitioning.

  • Jan 19, 2022
  • PeerJ
  • Caiqiong Wang +4
  • Conference Article
  • Citations3

Land Cover Semantic Segmentation of High-Resolution Gaofen-3 SAR Image

  • Jul 11, 2021
  • Xianzheng Shi +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.